出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：With the rapid development of Internet, Web search has been taken an important role in our ordinary life. In web search, mining frequent patterns in large database is a major research area. Due to increase of user activities on web, web-searching methods, to predict the next request of user visits in web pages plays a major role. Web searching methods are helpful to provide quality results, timely answer and also offer a customized navigation. In web search, Association rule mining is an important data analysis method to discover associated web pages. Most of the researchers implemented association mining using Apriori algorithm with binary representation. The problem of this approach is not address the issue like the navigation order of web pages. To overcome this problem researchers proposed a weighted Apriori to maintain navigation order but unable to produce optimal results. With the goal of a most favorable result we proposed a novel approach which combines weighted Apriori and dynamic programming. The experimental result shows that this approach maintains the navigation order of web pages and achieves a best solution. The proposed technique enhances the web site effectiveness, increases the user browsing knowledge, improves the prediction accuracy and decreases the computational complexities.
关键词：Web usage mining; Web page prediction; Dynamic Programming; Weighted Association Rule ;Mining (WARM); Improved Apriori Algorithm.
